RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 12:12:47 +01:00
Code Issues Projects Releases Wiki Activity
42,088 Commits 4 Branches 5 Tags 704 MiB
a99dc2692a
Commit Graph

25382 Commits

Author SHA1 Message Date
Chris Lattner
39f881ab69 fix typo noticed by sdt 
llvm-svn: 57644
 2008-10-16 17:02:50 +00:00
Gabor Greif
2fa8672ee6 Introduce a typing refinenement on tagged data 
using the 'volatile' qualifier. This should not have any operational consequences
on code, because tags should always be stripped off (giving a non-volatile pointer)
before dereferencing. The new qualification is there to catch some attempts to use
tagged pointers in a context where an untagged pointer is appropriate.

Notably this approach does not catch dereferencing of tagged pointers, but helps
in separating the two concepts a bit.

llvm-svn: 57641
 2008-10-16 15:33:02 +00:00
Duncan Sands
1349af7df4 Fix warnings about mb/me being potentially used 
uninitialized in these functions with gcc-4.3.

llvm-svn: 57635
 2008-10-16 13:02:33 +00:00
Duncan Sands
e6315b4179 Fix "large integer implicitly truncated to unsigned type" 
warning on x86-64 with gcc-4.3.

llvm-svn: 57634
 2008-10-16 09:14:58 +00:00
Chris Lattner
9afb6adf17 add some notes 
llvm-svn: 57631
 2008-10-16 07:04:06 +00:00
Chris Lattner
9d39b11d10 add some notes and a file to collect unimplemented features in the 
x86 backend.  These will all be answered with "patches welcome", so
a PR doesn't help drive them along.

llvm-svn: 57630
 2008-10-16 06:46:12 +00:00
Chris Lattner
562984c110 mark some targets as experimental. Andrew, if you think that Alpha is 
basically working, feel free to remove the tag.  The other targets have
really basic things that break them.

llvm-svn: 57628
 2008-10-16 06:16:50 +00:00
Chris Lattner
6d79672ba0 Verify prefetch arguments, PR2576. 
llvm-svn: 57626
 2008-10-16 06:00:36 +00:00
Chris Lattner
3048ccc1f9 apply Eli's patch for PR2165 and provide a testcase. 
llvm-svn: 57625
 2008-10-16 05:26:51 +00:00
Dan Gohman
86527c1834 Const-ify several TargetInstrInfo methods. 
llvm-svn: 57622
 2008-10-16 01:49:15 +00:00
Dan Gohman
991376be85 Remove an unused variable. 
llvm-svn: 57621
 2008-10-16 01:47:47 +00:00
Dan Gohman
11c8a9a63a Fix Instruction::isIdenticalTo and isSameOperationAs to recognize 
additional information in Loads, Stores, Calls, Invokes,
InsertValueInsts, and ExtractValueInsts.

llvm-svn: 57620
 2008-10-16 01:24:45 +00:00
Dan Gohman
3526f97d13 Rename AliasSet to SubRegs, to reflect changes in the surrounding code. 
llvm-svn: 57618
 2008-10-16 01:06:18 +00:00
Dan Gohman
46dafc2fb9 Move the include of MachineLocation.h into MachineModuleInfo.h 
because it declares a std::vector<MachineMove>, and strict
concept checking requires the definition of MachineMove to be
available.

llvm-svn: 57617
 2008-10-16 00:20:14 +00:00
Dan Gohman
8075c32a55 Fix a subtle bug in DeadMachineInstructionElim's liveness 
computation. A def of a register doesn't necessarily kill
live super-registers.

llvm-svn: 57614
 2008-10-16 00:11:23 +00:00
Dan Gohman
6dba6b2384 Fix the predicate for memop64 to be a regular load, not just 
an unindexed load.

llvm-svn: 57612
 2008-10-16 00:03:00 +00:00
Dan Gohman
6f40163d83 Teach instcombine's visitLoad to scan back several instructions 
to find opportunities for store-to-load forwarding or load CSE,
in the same way that visitStore scans back to do DSE. Also, define
a new helper function for testing whether the addresses of two
memory accesses are known to have the same value, and use it in
both visitStore and visitLoad.

These two changes allow instcombine to eliminate loads in code
produced by front-ends that frequently emit obviously redundant
addressing for memory references.

llvm-svn: 57608
 2008-10-15 23:19:35 +00:00
Dan Gohman
0c160fbe89 Correct the name of isTrapping in comments. 
llvm-svn: 57606
 2008-10-15 22:56:21 +00:00
Anton Korobeynikov
e322e95ecd Also properly handle linking of strong alias and weak global 
llvm-svn: 57595
 2008-10-15 20:10:50 +00:00
Anton Korobeynikov
d514695f79 Properly handle linking of strong alias with weak function, this fixes PR2883 
llvm-svn: 57594
 2008-10-15 20:10:08 +00:00
Dan Gohman
df18b6f3db Fix a missing space after the return type in invoke statements. 
This fixes PR2894.

llvm-svn: 57589
 2008-10-15 18:02:08 +00:00
Chris Lattner
2ce4f1e7ad move PR1941 here. 
llvm-svn: 57586
 2008-10-15 16:33:52 +00:00
Chris Lattner
866578b51b move PR1604 here. 
llvm-svn: 57582
 2008-10-15 16:06:03 +00:00
Chris Lattner
4ccc775d89 move PR1488 into this file. 
llvm-svn: 57579
 2008-10-15 16:02:15 +00:00
Nuno Lopes
fcab7d3d0c regenerate 
llvm-svn: 57577
 2008-10-15 12:05:02 +00:00
Nuno Lopes
8d27c6100b fix memleak in GetForwardRefForGlobal() 
llvm-svn: 57576
 2008-10-15 12:04:36 +00:00
Nuno Lopes
5b1a422162 regenerate 
llvm-svn: 57575
 2008-10-15 11:20:21 +00:00
Nuno Lopes
067c8791fe fix memleak in getTypeVal() 
llvm-svn: 57574
 2008-10-15 11:19:34 +00:00
Nuno Lopes
970117385a regenerate 
llvm-svn: 57573
 2008-10-15 11:11:12 +00:00
Nuno Lopes
0e2359f53d fix memleak in ResolveTypeTo() 
llvm-svn: 57572
 2008-10-15 11:10:21 +00:00
Dan Gohman
65702b2eb8 Now that predicates can be composed, simplify several of 
the predicates by extending simple predicates to create
more complex predicates instead of duplicating the logic
for the simple predicates.

This doesn't reduce much redundancy in DAGISelEmitter.cpp's
generated source yet; that will require improvements to
DAGISelEmitter.cpp's instruction sorting, to make it more
effectively group nodes with similar predicates together.

llvm-svn: 57565
 2008-10-15 06:50:19 +00:00
Chris Lattner
33e7093540 regenerate 
llvm-svn: 57561
 2008-10-15 06:16:57 +00:00
Chris Lattner
9449f199b3 Fix the .ll grammar rules to allow any type before an 'i32', not just an 
integer type.  Invalid things like 'float 42' are now rejected by the
semantic analysis in the productions not the parser.  This fixes PR2733.

llvm-svn: 57560
 2008-10-15 06:16:45 +00:00
Chris Lattner
33079f9c37 regenerate 
llvm-svn: 57559
 2008-10-15 06:03:48 +00:00
Chris Lattner
dc80d9772a Eliminate the "IntType ::= INTTYPE" production, just use 
INTTYPE everywhere.

llvm-svn: 57558
 2008-10-15 06:03:37 +00:00
Chris Lattner
d91c01484c add a note 
llvm-svn: 57557
 2008-10-15 05:53:25 +00:00
Chris Lattner
7194e8406a add support for folding immediates into stores when they 
are due to argument passing in calls.  This is significant because
it hits all immediate arguments to calls on x86-32.

llvm-svn: 57556
 2008-10-15 05:38:32 +00:00
Chris Lattner
214643296b fold immediates into stores in simple cases, this produces diffs like 
this:

-	movl	$0, %eax
-	movl	%eax, _yy_n_chars
+	movl	$0, _yy_n_chars

llvm-svn: 57555
 2008-10-15 05:30:52 +00:00
Chris Lattner
5716b8daa4 fold compare of null pointer into compare with 0. 
llvm-svn: 57553
 2008-10-15 05:18:04 +00:00
Chris Lattner
928e8e5092 Some minor cleanups: 
1. Compute action in X86SelectSelect based on MVT instead of type.
2. Use TLI.getValueType(..) instead of MVT::getVT(..) because the former
   handles pointers and the later doesn't.
3. Don't pass TLI into isTypeLegal, since it already has access to it as 
   an ivar.

#2 gives fast isel some minor new functionality: handling load/stores of
pointers.

llvm-svn: 57552
 2008-10-15 05:07:36 +00:00
Chris Lattner
da69b5e401 Use switch on VT instead of Type* comparisons. 
llvm-svn: 57551
 2008-10-15 04:32:45 +00:00
Chris Lattner
052e062f08 Use X86FastEmitCompare for FCMP_OEQ and FCMP_UNE: it doesn't 
change the generated code, but makes the code simpler.

llvm-svn: 57550
 2008-10-15 04:29:23 +00:00
Chris Lattner
d7024dafbf refactor compare emission out into a new X86FastEmitCompare method, 
which makes it easy to share the compare/imm folding logic with 'setcc'.
This shaves a bunch of instructions off the common select case, which
happens a lot in llvm-gcc.

llvm-svn: 57549
 2008-10-15 04:26:38 +00:00
Chris Lattner
cbea6edde5 Fold immediates into compares when possible, producing "cmp $4, %eax" instead of 
loading 4 into a register and then doing the compare.

llvm-svn: 57548
 2008-10-15 04:13:29 +00:00
Chris Lattner
905dbd0dea more minor refactoring of X86SelectBranch, no functionality change. 
llvm-svn: 57547
 2008-10-15 04:02:26 +00:00
Chris Lattner
99d88895b6 factor buildmi calls in X86SelectBranch 
llvm-svn: 57546
 2008-10-15 03:58:05 +00:00
Chris Lattner
97e96bcca0 factor some more BuildMI's in X86SelectCmp 
llvm-svn: 57545
 2008-10-15 03:52:54 +00:00
Chris Lattner
e66c12b3f5 factor some BuildMI calls, no functionality change. 
llvm-svn: 57544
 2008-10-15 03:47:17 +00:00
Dan Gohman
2ed6f318da Adjust whitespace in debug messages to be more consistent 
with other debug messages.

llvm-svn: 57543
 2008-10-15 02:57:38 +00:00
Evan Cheng
cb8b4e9dd4 - Add target lowering hooks that specify which setcc conditions are illegal, 
i.e. conditions that cannot be checked with a single instruction. For example,
SETONE and SETUEQ on x86.
- Teach legalizer to implement *illegal* setcc as a and / or of a number of
legal setcc nodes. For now, only implement FP conditions. e.g. SETONE is
implemented as SETO & SETNE, SETUEQ is SETUO | SETEQ.
- Move x86 target over.

llvm-svn: 57542
 2008-10-15 02:05:31 +00:00
Dan Gohman
c070ffc493 FastISel support for exception-handling constructs. 
- Move the EH landing-pad code and adjust it so that it works
   with FastISel as well as with SDISel.
 - Add FastISel support for @llvm.eh.exception and
   @llvm.eh.selector.

llvm-svn: 57539
 2008-10-14 23:54:11 +00:00
Daniel Dunbar
e11e618cc6 Prevent assert when using '"' in names (via hexadecimal). 
Update LangRef to mention \xx quoting in names.

llvm-svn: 57538
 2008-10-14 23:51:43 +00:00
Daniel Dunbar
f3b4f45878 Change getLLVMName to use raw_ostream & PrintLLVMName. 
- Avoids duplicated quotification code.
 - Remove QuoteNameIfNeeded.
 - No functionality change.

llvm-svn: 57537
 2008-10-14 23:28:09 +00:00
Dale Johannesen
19407daf55 Accept -march=i586, because gcc does (a synonym 
for pentium).  Fixes
gcc.target/i386/20000720-1.c
gcc.target/i386/pr26826.c

llvm-svn: 57528
 2008-10-14 22:06:33 +00:00
Evan Cheng
3faedff2de Rename LoadX to LoadExt. 
llvm-svn: 57526
 2008-10-14 21:26:46 +00:00
Jim Grosbach
d0ff59ec42 Update ARM Insn encoding to get endian-ness to match the documentation (31-0 left to right) 
llvm-svn: 57524
 2008-10-14 20:36:24 +00:00
Dan Gohman
9543edc4ef Fix command-line option printing to print two spaces where needed, 
instead of requiring all "short description" strings to begin with
two spaces. This makes these strings less mysterious, and it fixes
some cases where short description strings mistakenly did not
begin with two spaces.

llvm-svn: 57521
 2008-10-14 20:25:08 +00:00
Evan Cheng
591baeed7c Combine (fcmp cc0 x, y) | (fcmp cc1 x, y) into a single fcmp when possible. 
llvm-svn: 57515
 2008-10-14 18:44:08 +00:00
Evan Cheng
778b47e6c0 - Somehow I forgot about one / une. 
- Renumber fcmp predicates to match their icmp counterparts.
- Try swapping operands to expose more optimization opportunities.

llvm-svn: 57513
 2008-10-14 18:13:38 +00:00
Evan Cheng
39a819027c Fix indentation. 
llvm-svn: 57508
 2008-10-14 17:15:39 +00:00
Evan Cheng
91528965e7 Optimize anding of two fcmp into a single fcmp if the operands are the same. e.g. uno && ueq -> ueq 
ord && olt -> olt
     ord && ueq -> oeq

llvm-svn: 57507
 2008-10-14 17:15:11 +00:00
Nuno Lopes
08a1a82acc little optimization: reuse getPointerToGlobalIfAvailable(CGV) value in emitGlobals() 
llvm-svn: 57484
 2008-10-14 10:04:52 +00:00
Dan Gohman
e08e0dcfcc When doing the very-late shift-and address-mode optimization, 
create a new DAG node to represent the new shift to keep the
DAG consistent, even though it'll almost always be folded into
the address.

If a user of the resulting address has multiple uses, the
nodes may get revisited by a later MatchAddress call, in which
case DAG inconsistencies do matter.

This fixes PR2849.

llvm-svn: 57465
 2008-10-13 20:52:04 +00:00
Evan Cheng
de99d94c58 FIX PR2794. Make sure SIGN_EXTEND_INREG nodes introduced by LegalizeSetCCOperands are leglized. Patch by Richard Pennington. 
llvm-svn: 57460
 2008-10-13 18:46:18 +00:00
Evan Cheng
731f400eac Also update sub-register intervals after a trivial computation is rematt'ed for a copy instruction. PR2775. 
llvm-svn: 57458
 2008-10-13 18:35:52 +00:00
Matthijs Kooijman
b86d48c717 Make InstructionCombining::getBitCastOperand() recognize GEP instructions and 
constant expression with all zero indices as being the same as a bitcast.

llvm-svn: 57442
 2008-10-13 15:17:01 +00:00
Matthijs Kooijman
1ea1008e1f * Make TargetLowering not crash when TargetMachine::getTargetAsmInfo() returns 
null. This assumes that any target that does not have AsmInfo, does not
   support "LocAndDot".

llvm-svn: 57438
 2008-10-13 12:41:46 +00:00
Matthijs Kooijman
28ae70be64 Make MachineFunction not crash when TargetMachine::getRegisterInfo() returns 
NULL, but just hide some debug output then.

llvm-svn: 57437
 2008-10-13 12:37:16 +00:00
Gabor Greif
5f75f1372e do not use deprecated interfaces 
llvm-svn: 57433
 2008-10-13 10:21:17 +00:00
Nick Lewycky
ed4cd79ffc Disallow the construction of SCEVs with could-not-compute operands. Catch CNCs 
returned by BinomialCoefficient and don't try to operate with them. This
replaces the previous fix for PR2857.

llvm-svn: 57431
 2008-10-13 03:58:02 +00:00
Chris Lattner
16c0109fd4 calls can be supported. 
llvm-svn: 57428
 2008-10-13 01:59:13 +00:00
Dale Johannesen
7fbfe2a371 Change TAG_ names to DW_TAG for gcc (testsuite) compatibility. 
llvm-svn: 57425
 2008-10-12 21:23:01 +00:00
Owen Anderson
dbb4904467 Fix a bug in live-in detection that caused lost-copy problems to show up. 
llvm-svn: 57424
 2008-10-12 20:39:30 +00:00
Anton Korobeynikov
6204f4ac43 Update size of inst correctly with segment override. 
llvm-svn: 57414
 2008-10-12 10:30:11 +00:00
Owen Anderson
fe70fff286 Add special-case code to allow null-guards on calls to malloc. 
llvm-svn: 57413
 2008-10-12 08:10:46 +00:00
Owen Anderson
86d9a902dc Make Escape Analysis work for any pointer. 
llvm-svn: 57412
 2008-10-12 07:33:29 +00:00
Dale Johannesen
2d23786266 Change Dwarf comments starting with AT_ to DW_AT_ to 
match gcc.  Helps with the testsuite.

llvm-svn: 57410
 2008-10-12 06:20:47 +00:00
Owen Anderson
9b86d152be Fix crashes and infinite loops. 
llvm-svn: 57408
 2008-10-12 06:03:38 +00:00
Owen Anderson
d724368eeb Duncan convinced me that it's not possible to transform control-based escapes into 
data-based ones.  Just be conservative when analyzing control-based escapes.

llvm-svn: 57400
 2008-10-12 03:59:45 +00:00
Chris Lattner
3c8eace4da fix typo 
llvm-svn: 57388
 2008-10-11 23:59:03 +00:00
Chris Lattner
7a61ef92f5 Fix PR2697 by rewriting the '(X / pos) op neg' logic. This also changes 
a couple other cases for clarity, but shouldn't affect correctness.

Patch by Eli Friedman!

llvm-svn: 57387
 2008-10-11 22:55:00 +00:00
Chris Lattner
7910d59d44 Change CALLSEQ_BEGIN and CALLSEQ_END to take TargetConstant's as 
parameters instead of raw Constants.  This prevents the constants from
being selected by the isel pass, fixing PR2735.

llvm-svn: 57385
 2008-10-11 22:08:30 +00:00
Chris Lattner
3d1cdfc99e rearrange some code. 
llvm-svn: 57384
 2008-10-11 22:07:19 +00:00
Duncan Sands
f175d9eae0 Fix comment typo. 
llvm-svn: 57381
 2008-10-11 19:34:24 +00:00
Anton Korobeynikov
d8b3e6f0ce Add ability to override segment (mostly for code emitter purposes). 
llvm-svn: 57380
 2008-10-11 19:09:15 +00:00
Daniel Dunbar
73ceb8010b Unbreak DbgStopPointInst::getFileName(). 
llvm-svn: 57373
 2008-10-11 06:40:56 +00:00
Chris Lattner
2f2ef3f25f simplify comparison 
llvm-svn: 57371
 2008-10-11 00:08:02 +00:00
Dale Johannesen
03d0a7d70c Fix SSE4.1 roundss, roundsd. While the instructions have 
the same pattern as roundpd/roundps, the Intel compiler 
builtins do not:  rounds* has an extra operand.  Fixes
gcc.target/i386/sse4_1-rounds[sd]-[1234].c

llvm-svn: 57370
 2008-10-10 23:51:03 +00:00
Devang Patel
255fee3bce Check loop exit predicate properly while eliminating one iteration loop. 
This patch fixes PR 2869

llvm-svn: 57369
 2008-10-10 22:02:57 +00:00
Anton Korobeynikov
e44fccb2f0 Fix a thinko and unbreak sparc default CC 
llvm-svn: 57368
 2008-10-10 21:47:37 +00:00
Dale Johannesen
0c6ea38b92 Remove some overzealous checks that were rejecting 
valid comments in inline assembly.
gcc.target/i386/20011009-1.c

llvm-svn: 57365
 2008-10-10 21:04:42 +00:00
Anton Korobeynikov
f5398df73c Extend set of return registers on sparc until someone will implement MRV support there. At least, this will allow libgcc compile, however we are not ABI-compatible with stuff compiled with native gcc. 
llvm-svn: 57364
 2008-10-10 20:30:14 +00:00
Anton Korobeynikov
1ead869e67 Ignore extra 'r' modifier for now 
llvm-svn: 57363
 2008-10-10 20:29:50 +00:00
Anton Korobeynikov
ffdc3498b4 Use expand for smul_lohi for now 
llvm-svn: 57362
 2008-10-10 20:29:31 +00:00
Anton Korobeynikov
8ed548b24a Add rudimentary support for 'r' register operand 
llvm-svn: 57359
 2008-10-10 20:28:10 +00:00
Anton Korobeynikov
ba8bb3e12f Cleanup 
llvm-svn: 57358
 2008-10-10 20:27:31 +00:00
Oscar Fuentes
32e927030e CMake: updated lib/Analysis/CMakeLists.txt. 
llvm-svn: 57357
 2008-10-10 18:51:36 +00:00
Mon P Wang
dc1aa21e4e Revert r57340 move guard mutex in getPointerToFunction as this can cause 
deadlock issues with java

llvm-svn: 57356
 2008-10-10 18:07:10 +00:00
Nuno Lopes
cc4f37aa68 fix memleak by cleaning the global sets on pass exit 
llvm-svn: 57353
 2008-10-10 16:25:50 +00:00
Anton Korobeynikov
6054846989 Add rudimentary asmprinter support for printing inline asm operands for sparc. 
llvm-svn: 57346
 2008-10-10 10:15:03 +00:00
Anton Korobeynikov
a12d563611 Add dummy 'm' inline asm constraint handler for Sparc. I'm not sure, whether it is correct, however :) 
llvm-svn: 57345
 2008-10-10 10:14:47 +00:00
Anton Korobeynikov
8cfd14b138 Cleanup 
llvm-svn: 57344
 2008-10-10 10:14:15 +00:00
Owen Anderson
5a5a9162e6 Add a basic intra-procedural escape analysis. This hasn't be extensively tested yet, but feedback is welcome. 
llvm-svn: 57342
 2008-10-10 08:36:25 +00:00
Mon P Wang
6c79c8e822 Moved guard mutex upwards to guard materializing a function 
in getPointerToFunction

llvm-svn: 57340
 2008-10-10 01:47:42 +00:00
Mon P Wang
3b3ab0fa30 Added missing print functions that take a raw_ostream 
llvm-svn: 57339
 2008-10-10 01:43:55 +00:00
Dale Johannesen
cc34c2da3a Generated files for previous checkin. 
llvm-svn: 57331
 2008-10-09 23:01:34 +00:00
Dale Johannesen
075a62519f Add a "loses information" return value to APFloat::convert 
and APFloat::convertToInteger.  Restore return value to
IEEE754.  Adjust all users accordingly.

llvm-svn: 57329
 2008-10-09 23:00:39 +00:00
Dale Johannesen
9e57068854 Rename APFloat::convertToAPInt to bitcastToAPInt to 
make it clearer what the function does.  No functional
change.

llvm-svn: 57325
 2008-10-09 18:53:47 +00:00
Nick Lewycky
843c7dfe05 Don't drop alignment on globals when cloning. 
llvm-svn: 57320
 2008-10-09 06:27:14 +00:00
Chris Lattner
284ae75537 get CodeGen/Alpha/mul128.ll to work. 
llvm-svn: 57318
 2008-10-09 04:50:56 +00:00
Dale Johannesen
9c6ffd55b4 Align EH tables before label is emitted, not after, 
thus aligning the label.

llvm-svn: 57310
 2008-10-08 21:50:21 +00:00
Dale Johannesen
817eff07b1 (re)Put const weak strings in appropriate section on Darwin. 
g++dg/abi/key2.C

llvm-svn: 57309
 2008-10-08 21:49:47 +00:00
Nuno Lopes
a4813e472c dont specialize weak functions and the like 
llvm-svn: 57305
 2008-10-08 18:45:59 +00:00
Jim Grosbach
974799922e Comment to be explicit that the enumeration values for CondCodes matter. 
llvm-svn: 57295
 2008-10-08 16:24:35 +00:00
Duncan Sands
bc53ce331a Use template to distinguish between function variants. 
GCC 4.4.0 gives an error on the "int" declaration for example
saying that it has already been declared (using the "short"
one). Using templates here allow the compiler to distinguish
between the function to choose.

Also, "llvm/Support/DataTypes.h" was not included, leading to
error messages about not knowing "uint32_t" for example.

Patch by Samuel Tardieu.

llvm-svn: 57292
 2008-10-08 07:44:52 +00:00
Duncan Sands
8f296a3788 Add <cstdio> include where needed by gcc-4.4. 
Patch by Samuel Tardieu.

llvm-svn: 57291
 2008-10-08 07:23:46 +00:00
Chris Lattner
293590ca07 regenerate 
llvm-svn: 57290
 2008-10-08 06:44:45 +00:00
Chris Lattner
4afce47e9b Add missing semicolumns in parser rules, those missing semicolumns 
are required to compile with the latest Bison.

Patch by Samuel Tardieu!

llvm-svn: 57289
 2008-10-08 06:44:36 +00:00
Chris Lattner
0aa4423c8c Add parentheses to avoid warnings in GCC 4.4.0, 
patch by Samuel Tardieu!

llvm-svn: 57288
 2008-10-08 06:42:28 +00:00
Owen Anderson
7f99714393 Fix the case where an instruction is not properly marked as using all registers that alias its inputs. 
llvm-svn: 57286
 2008-10-08 04:30:51 +00:00
Dan Gohman
08e60cee90 Remove -disable-fast-isel. Use cl::boolOrDefault with -fast-isel 
instead.

So now: -fast-isel or -fast-isel=true enable fast-isel, and
-fast-isel=false disables it. Fast-isel is also on by default
with -fast, and off by default otherwise.

llvm-svn: 57270
 2008-10-07 23:00:56 +00:00
Dan Gohman
c65ca09308 Add MBB successors and physreg Uses in the same order that 
SDISel typically adds them in. This makes it a little easier
to compare FastISel output with SDISel output.

llvm-svn: 57266
 2008-10-07 22:10:33 +00:00
Dan Gohman
6d98c5ab31 Avoid emitting redundant materializations of integer constants 
for things like null pointers, which at this level aren't
different from regular integer constants.

llvm-svn: 57265
 2008-10-07 22:03:27 +00:00
Dan Gohman
2561119124 Instead of emitting an implicit use for the super-register of 
X86::CL that was used, emit an EXTRACT_SUBREG from the CL
super-register to CL. This more precisely describes how the
CL register is being used.

llvm-svn: 57264
 2008-10-07 21:50:36 +00:00
Jim Grosbach
8ac554209f Unconditional branch instruction encoding fix. Needs to use ABI, not AXI, to get the proper opcode bits. 
llvm-svn: 57262
 2008-10-07 21:08:09 +00:00
Jim Grosbach
5fb8bb7434 need ARM.h for ARMCC definition 
llvm-svn: 57261
 2008-10-07 21:01:51 +00:00
Owen Anderson
c9a628af26 Add an option to enable StrongPHIElimination, for ease of testing. 
llvm-svn: 57259
 2008-10-07 20:22:28 +00:00
Jim Grosbach
d44d20be6e Encode the conditional execution predicate when JITing. 
llvm-svn: 57258
 2008-10-07 19:05:35 +00:00
Dale Johannesen
3d2e449078 Model hardwired inputs & outputs of x86 8-bit divides correctly. 
Fixes local RA miscompilation of gcc.c-torture/execute/20020904-1.c -O0.

llvm-svn: 57257
 2008-10-07 18:54:28 +00:00
Andrew Lenharth
66cc9d5e53 Use Dan's supperior check 
llvm-svn: 57255
 2008-10-07 18:27:23 +00:00
Andrew Lenharth
c83731e00a Correctly set attributes when removing args during cloning. Fixes PR2765 
llvm-svn: 57254
 2008-10-07 18:08:38 +00:00
Jim Grosbach
61f8207ac9 Clarify naming and correct conditional so that CMP and CMN instructions get the Rn operand encoded properly 
llvm-svn: 57252
 2008-10-07 17:42:09 +00:00
Jim Grosbach
a52546fec4 Fix Opcode values of CMP and CMN 
llvm-svn: 57251
 2008-10-07 17:40:46 +00:00
Andrew Lenharth
950618a347 No need for |= 
llvm-svn: 57249
 2008-10-07 17:11:29 +00:00
Andrew Lenharth
2399c6cb95 Use ADDC if it is valid at any smaller size. Do it right this time 
llvm-svn: 57248
 2008-10-07 17:09:16 +00:00
Andrew Lenharth
84166420cc Use ADDC if it is valid at any smaller size. fixes test/Codegen/Generic/i128-addsub.ll on x86 
llvm-svn: 57247
 2008-10-07 17:03:15 +00:00
Anders Carlsson
a9c42526f8 Certain patterns involving the "movss" instruction were marked as requiring SSE2, when in reality movss is an SSE1 instruction. 
llvm-svn: 57246
 2008-10-07 16:14:11 +00:00
Andrew Lenharth
c00c2a0058 Expand arith on machines without carry flags 
llvm-svn: 57243
 2008-10-07 14:15:42 +00:00
Andrew Lenharth
7a997d1cfd Note that ADDC and company don't actually expand yet (missing in legalize 
llvm-svn: 57226
 2008-10-07 02:10:26 +00:00
Dale Johannesen
3b86d974bc Mark negative-zero-to-int conversion as Inexact, 
since -0.0 can't be represented as an int.
This prevents llvm from reducing -0.0 to a
load-and-convert of int 0.  Fixes
ieee.exp/mzero[2356].c in gcc testsuite.

llvm-svn: 57224
 2008-10-07 00:40:01 +00:00
Dan Gohman
188af3ae0d Correctly handle calls with no return values. This fixes 
2006-01-23-UnionInit on x86-64 when inlining is not enabled.

llvm-svn: 57223
 2008-10-07 00:12:37 +00:00
Devang Patel
378c8633e5 Fix typo, fix PR 2865. 
llvm-svn: 57221
 2008-10-06 23:22:54 +00:00
Dale Johannesen
40d00c0979 Be more precise about which conversions of NaNs 
are Inexact.  (These are not Inexact as defined
by IEEE754, but that seems like a reasonable way
to abstract what happens:  information is lost.)

llvm-svn: 57218
 2008-10-06 22:59:10 +00:00
Evan Cheng
88d76ffe8a Fix PR2850 and PR2863. Only generate movddup for 128-bit SSE vector shuffles. 
llvm-svn: 57210
 2008-10-06 21:13:08 +00:00
Dale Johannesen
24ea5f2be7 Temporarily revert functionality change from my previous patch; 
it is too aggressive.

llvm-svn: 57203
 2008-10-06 20:43:48 +00:00
Devang Patel
ca66d093c0 Remove interfaces implemented by dead pass from the list of available passes. 
Patch By Matthijs Kooijman.

llvm-svn: 57202
 2008-10-06 20:36:36 +00:00
Dale Johannesen
89329a1d0a Mark shortening NaN conversions as Inexact. PR 2856. 
Improve description of unsupported formats.

llvm-svn: 57185
 2008-10-06 18:22:29 +00:00
Devang Patel
07a9ce22e4 It is possible that all functions in one module are not being 
optimized for size. Set OptForSize for each function separately.

llvm-svn: 57182
 2008-10-06 18:03:39 +00:00
Dan Gohman
8b33abdd5b Don't dereference the end() iterator. Thanks to 
ENABLE_EXPENSIVE_CHECKS for finding this.

llvm-svn: 57181
 2008-10-06 18:00:07 +00:00
Devang Patel
4f91b766d2 Remove unncessary isDeclaration() checks. 
llvm-svn: 57179
 2008-10-06 17:30:07 +00:00
Matthijs Kooijman
12cd5d041d Allow scalarrepl to treat an all-zero GEP just as bitcast. 
This includes not marking a GEP involving a vector as unsafe, but only when it
has all zero indices. This allows scalarrepl to work in a few more cases.

llvm-svn: 57177
 2008-10-06 16:23:31 +00:00
Chris Lattner
8e41e3ac13 reorder #include order, patch by Kenneth Boyd! 
llvm-svn: 57148
 2008-10-06 03:54:25 +00:00
Chris Lattner
5d6871b940 Add #include to get alloca, patch by Kenneth Boyd! 
llvm-svn: 57147
 2008-10-06 03:53:16 +00:00
Chris Lattner
4622ca2262 fix an incorrect and extremely confusing error message 
llvm-svn: 57123
 2008-10-05 18:24:03 +00:00
Chris Lattner
1e4f7de3b6 make the autoupgrade code for ret attributes dramatically simpler 
and actually work.  We can now read the llvm 2.3 bc file from PR2849

llvm-svn: 57122
 2008-10-05 18:22:09 +00:00
Nuno Lopes
4cf7f0e3cd regenerate 
llvm-svn: 57114
 2008-10-05 16:49:34 +00:00
Nuno Lopes
9e274c3532 clean ArgTypeListI production: free the PATypeHolder 
llvm-svn: 57113
 2008-10-05 16:49:03 +00:00
Anton Korobeynikov
8106145480 Emit type-correct constant null. Also fix a typo. 
Patch by Robert G. Jakabosky!

llvm-svn: 57110
 2008-10-05 15:07:06 +00:00
Anton Korobeynikov
1f7e8162d9 Fix weird think-o and unbreak build on all gcc-3.4.x-based platforms (e.g. mingw) 
llvm-svn: 57106
 2008-10-05 08:53:29 +00:00
Chris Lattner
ed0f84ee2d this case is matched now. 
llvm-svn: 57096
 2008-10-05 02:16:12 +00:00
Chris Lattner
107e8f8b60 rewrite bswap matching to be more general, allowing arbitrary 
shifting and masking inside a bswap expr.  This allows it to handle
the cases from PR2842, which involve the intermediate 'or' 
expressions being shifted, not just the input value.

llvm-svn: 57095
 2008-10-05 02:13:19 +00:00
Chris Lattner
6fae76bbf3 fix a bug where the bswap matcher could match a case involving 
ashr.  It should only apply to lshr.

llvm-svn: 57089
 2008-10-05 00:50:57 +00:00
Chris Lattner
576e29c87d wrap some long lines and expand i32 mul's to libcalls, inspired by a 
patch by Mikael Lepisto!

llvm-svn: 57077
 2008-10-04 21:27:46 +00:00
Oscar Fuentes
4bf1c53073 CMake: Reflected changes on source file structure. New plugin support 
for llvmc2 incomplete.

llvm-svn: 57076
 2008-10-04 21:18:50 +00:00
Duncan Sands
e22385630e Ignore loads from and stores to local memory (i.e. allocas) 
when deciding whether to mark a function readnone/readonly.
Since the pass is currently run before SROA, this may be
quite helpful.  Requested by Chris on IRC.

llvm-svn: 57050
 2008-10-04 13:24:24 +00:00
Nick Lewycky
53e751fcba Allow the construction of SCEVs with SCEVCouldNotCompute operands, by 
implementing folding. Fixes PR2857.

llvm-svn: 57049
 2008-10-04 11:19:07 +00:00
Anton Korobeynikov
4cc9051fbb Revert r56675 - it breaks unwinding runtime everywhere. 
llvm-svn: 57048
 2008-10-04 11:09:36 +00:00
Argyrios Kyrtzidis
8614f628d2 Add implementations for sys::Memory::setWritable and sys::Memory::setExecutable on Win32 platform. 
llvm-svn: 57047
 2008-10-04 08:15:32 +00:00
Argyrios Kyrtzidis
b9e76c172c Fix compilation error on MSVC. 
llvm-svn: 57046
 2008-10-04 08:11:49 +00:00
Dan Gohman
5944450d5f Fix fast-isel's handling of atomic instructions. They may 
expand to multiple basic blocks, in which case fast-isel
needs to informed of which block to use as it resumes
inserting instructions.

llvm-svn: 57040
 2008-10-04 00:56:36 +00:00
Dan Gohman
638a8001c8 Fix a bug in the local allocator's liveness computation where it 
was setting kill flags on tied uses in two-address instructions.
The kill flags were causing the allocator to think it could
allocate the use and its tied def in different registers.

llvm-svn: 57039
 2008-10-04 00:31:14 +00:00
Dale Johannesen
dc83b95ba5 Make atomic Swap work, 64-bit on x86-32. 
Make it all work in non-pic mode.

llvm-svn: 57034
 2008-10-03 22:25:52 +00:00
Dan Gohman
700611dfc6 Clean up some multiple-return-value code that is no longer 
applicable.

llvm-svn: 57033
 2008-10-03 22:21:24 +00:00
Devang Patel
0d22d8ebdb Fix function attribute verification check. 
Thanks Duncan!

llvm-svn: 57029
 2008-10-03 21:11:02 +00:00
Dale Johannesen
27d8955b8f Pass MemOperand through for 64-bit atomics on 32-bit, 
incidentally making the case where the memop is a
pointer deref work.  Fix cmp-and-swap regression.

llvm-svn: 57027
 2008-10-03 19:41:08 +00:00
Devang Patel
55401473f9 Nick Lewycky's patch. 
While hosting instruction check PHI node.

llvm-svn: 57025
 2008-10-03 18:57:37 +00:00
Dan Gohman
dc99a744fd Use -1ULL instead of uint64_t(-1), at Anton's suggestion. 
llvm-svn: 57021
 2008-10-03 17:56:45 +00:00
Devang Patel
2bed4d4ca0 Verify function attributes. 
llvm-svn: 57020
 2008-10-03 17:50:00 +00:00
Evan Cheng
d572afd76c Fix typos pointed out by Duncan. Also untabify these files. 
llvm-svn: 57018
 2008-10-03 17:11:58 +00:00
Daniel Dunbar
40fb36a42c Unbreak build. 
llvm-svn: 57017
 2008-10-03 17:11:57 +00:00
Dan Gohman
00034b1416 Avoid creating two TargetLowering objects for each target. 
Instead, just create one, and make sure everything that needs
it can access it. Previously most of the SelectionDAGISel
subclasses all had their own TargetLowering object, which was
redundant with the TargetLowering object in the TargetMachine
subclasses, except on Sparc, where SparcTargetMachine
didn't have a TargetLowering object. Change Sparc to work
more like the other targets here.

llvm-svn: 57016
 2008-10-03 16:55:19 +00:00
Dan Gohman
e41ac02dce Remove an unused field. 
llvm-svn: 57014
 2008-10-03 16:17:33 +00:00
Jim Grosbach
a49386d8e7 On Darwin ARM, memory needs special handling to do JIT. This patch expands 
this handling to work properly for modifying stub functions, relocations
back to entry points after JIT compilation, etc..

llvm-svn: 57013
 2008-10-03 16:17:20 +00:00
Jim Grosbach
d9ff019d3e Indexing off by one resulted in errant encoding of source register for 
reg->reg moves.

llvm-svn: 57011
 2008-10-03 15:53:56 +00:00
Jim Grosbach
e398f553b2 NeedStub/DoesntNeedStub logic was reversed, leading to not using a stub 
for global relocations that do need them (libc calls, for example).

llvm-svn: 57010
 2008-10-03 15:52:42 +00:00
Nuno Lopes
3fbdc238d6 regenerate 
llvm-svn: 57009
 2008-10-03 15:52:39 +00:00
Nuno Lopes
5cb07eb550 fix more memleaks in ResolveTypeTo() and ParseGlobalVariable() 
llvm-svn: 57008
 2008-10-03 15:51:46 +00:00
Nuno Lopes
263d218cd1 regenerate with bison 2.3 
llvm-svn: 57007
 2008-10-03 15:45:58 +00:00
Dan Gohman
30c5ce1b7d Switch the MachineOperand accessors back to the short names like 
isReg, etc., from isRegister, etc.

llvm-svn: 57006
 2008-10-03 15:45:36 +00:00
Nuno Lopes
949c7ea3e7 fix memleak in FunctionHeaderH 
llvm-svn: 57005
 2008-10-03 15:44:21 +00:00
Duncan Sands
00b25fea88 The result of getSetCCResultType (eg: i32) may be larger 
than the type an i1 is promoted to (eg: i8).  Account
for this.  Noticed by Tilmann Scheller on CellSPU; he
will hopefully take care of fixing this in LegalizeDAG
and adding a testcase!

llvm-svn: 56997
 2008-10-03 07:41:46 +00:00
Duncan Sands
5edd9b2350 Teach internalize to preserve the callgraph. 
Why?  Because it was there!

llvm-svn: 56996
 2008-10-03 07:36:09 +00:00
Nicolas Geoffray
c3efec61f5 Acquire the lock only when necessary. More precisely, do not acquire 
the lock when calling a method which may materialize the llvm::Function.

llvm-svn: 56995
 2008-10-03 07:27:08 +00:00
Owen Anderson
e98ca283b0 SplitBlock should only attempt to update LoopInfo if it is actually being used. 
llvm-svn: 56994
 2008-10-03 06:55:35 +00:00
Dan Gohman
68e27d0b27 Implement fast-isel support for zero-extending from i1. 
It turns out that this is a fairly common operation,
and it's easy enough to handle.

llvm-svn: 56990
 2008-10-03 01:28:47 +00:00
Dan Gohman
78ef9889c9 Fix X86FastISel to handle dynamic allocas that have avoided 
getting inserted into the ValueMap. This avoids infinite
recursion in some rare cases.

llvm-svn: 56989
 2008-10-03 01:27:49 +00:00
Dan Gohman
e75d14f8b0 Optimize conditional branches in X86FastISel. This replaces 
sequences like this:
       sete    %al
       testb   %al, %al
       jne     LBB11_1
with this:
       je      LBB11_1

llvm-svn: 56969
 2008-10-02 22:15:21 +00:00
Dan Gohman
bf63ae1e29 Add a new MachineBasicBlock utility function, isLayoutSuccessor, that 
can be used when deciding if a block can transfer control to another
via a fall-through instead of a branch.

llvm-svn: 56968
 2008-10-02 22:09:09 +00:00
Andrew Lenharth
106090d2a6 fix build gcc 4.3 
llvm-svn: 56965
 2008-10-02 20:15:08 +00:00
Owen Anderson
1c171e1d1c Use a multimap rather than a map for holding the list of copies to insert, so we don't lose copies when two of them have 
the same source.  I don't know what I was thinking when I wrote this originally.
Note: There's probably a more efficient way to do this, but I need to think about it some more, and about what determinism
guarantees need to be present.

llvm-svn: 56964
 2008-10-02 19:40:33 +00:00